arxiv:2505.21115
Maria Marina
zlatamaria
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
1 day ago
The Rogue Scalpel: Activation Steering Compromises LLM Safety
upvoted
a
paper
12 days ago
OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features
Organizations
models
0
None public yet
datasets
9
zlatamaria/geometry_companies_hallu_UC
Viewer
•
Updated
•
1.2k
•
25
zlatamaria/geometry_common_claim_hallu_UC
Viewer
•
Updated
•
4.45k
•
10
zlatamaria/geometry_cities_hallu_UC
Viewer
•
Updated
•
1.13k
•
9
zlatamaria/x-fact_hallu_UC
Viewer
•
Updated
•
1.13k
•
3
zlatamaria/WH_hallu_UC
Viewer
•
Updated
•
36.4k
•
7
zlatamaria/PopQA_hallu_UC
Viewer
•
Updated
•
5.49k
•
6
zlatamaria/Uhead_hallu_UC
Viewer
•
Updated
•
921
•
12
zlatamaria/AVeriTeC_hallu_UC
Viewer
•
Updated
•
349
•
4
zlatamaria/RuBQ
Viewer
•
Updated
•
1.19k
•
10